1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261
|
// SPDX-License-Identifier: GPL-2.0
/*
* linux/ipc/namespace.c
* Copyright (C) 2006 Pavel Emelyanov <[email protected]> OpenVZ, SWsoft Inc.
*/
#include <linux/ipc.h>
#include <linux/msg.h>
#include <linux/ipc_namespace.h>
#include <linux/rcupdate.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/user_namespace.h>
#include <linux/proc_ns.h>
#include <linux/sched/task.h>
#include "util.h"
/*
* The work queue is used to avoid the cost of synchronize_rcu in kern_unmount.
*/
static void free_ipc(struct work_struct *unused);
static DECLARE_WORK(free_ipc_work, free_ipc);
static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns)
{
return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES);
}
static void dec_ipc_namespaces(struct ucounts *ucounts)
{
dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES);
}
static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
struct ipc_namespace *old_ns)
{
struct ipc_namespace *ns;
struct ucounts *ucounts;
int err;
err = -ENOSPC;
again:
ucounts = inc_ipc_namespaces(user_ns);
if (!ucounts) {
/*
* IPC namespaces are freed asynchronously, by free_ipc_work.
* If frees were pending, flush_work will wait, and
* return true. Fail the allocation if no frees are pending.
*/
if (flush_work(&free_ipc_work))
goto again;
goto fail;
}
err = -ENOMEM;
ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT);
if (ns == NULL)
goto fail_dec;
err = ns_alloc_inum(&ns->ns);
if (err)
goto fail_free;
ns->ns.ops = &ipcns_operations;
refcount_set(&ns->ns.count, 1);
ns->user_ns = get_user_ns(user_ns);
ns->ucounts = ucounts;
err = mq_init_ns(ns);
if (err)
goto fail_put;
err = -ENOMEM;
if (!setup_mq_sysctls(ns))
goto fail_put;
if (!setup_ipc_sysctls(ns))
goto fail_mq;
err = msg_init_ns(ns);
if (err)
goto fail_ipc;
sem_init_ns(ns);
shm_init_ns(ns);
return ns;
fail_ipc:
retire_ipc_sysctls(ns);
fail_mq:
retire_mq_sysctls(ns);
fail_put:
put_user_ns(ns->user_ns);
ns_free_inum(&ns->ns);
fail_free:
kfree(ns);
fail_dec:
dec_ipc_namespaces(ucounts);
fail:
return ERR_PTR(err);
}
struct ipc_namespace *copy_ipcs(unsigned long flags,
struct user_namespace *user_ns, struct ipc_namespace *ns)
{
if (!(flags & CLONE_NEWIPC))
return get_ipc_ns(ns);
return create_ipc_ns(user_ns, ns);
}
/*
* free_ipcs - free all ipcs of one type
* @ns: the namespace to remove the ipcs from
* @ids: the table of ipcs to free
* @free: the function called to free each individual ipc
*
* Called for each kind of ipc when an ipc_namespace exits.
*/
void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
void (*free)(struct ipc_namespace *, struct kern_ipc_perm *))
{
struct kern_ipc_perm *perm;
int next_id;
int total, in_use;
down_write(&ids->rwsem);
in_use = ids->in_use;
for (total = 0, next_id = 0; total < in_use; next_id ) {
perm = idr_find(&ids->ipcs_idr, next_id);
if (perm == NULL)
continue;
rcu_read_lock();
ipc_lock_object(perm);
free(ns, perm);
total ;
}
up_write(&ids->rwsem);
}
static void free_ipc_ns(struct ipc_namespace *ns)
{
/*
* Caller needs to wait for an RCU grace period to have passed
* after making the mount point inaccessible to new accesses.
*/
mntput(ns->mq_mnt);
sem_exit_ns(ns);
msg_exit_ns(ns);
shm_exit_ns(ns);
retire_mq_sysctls(ns);
retire_ipc_sysctls(ns);
dec_ipc_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
ns_free_inum(&ns->ns);
kfree(ns);
}
static LLIST_HEAD(free_ipc_list);
static void free_ipc(struct work_struct *unused)
{
struct llist_node *node = llist_del_all(&free_ipc_list);
struct ipc_namespace *n, *t;
llist_for_each_entry_safe(n, t, node, mnt_llist)
mnt_make_shortterm(n->mq_mnt);
/* Wait for any last users to have gone away. */
synchronize_rcu();
llist_for_each_entry_safe(n, t, node, mnt_llist)
free_ipc_ns(n);
}
/*
* put_ipc_ns - drop a reference to an ipc namespace.
* @ns: the namespace to put
*
* If this is the last task in the namespace exiting, and
* it is dropping the refcount to 0, then it can race with
* a task in another ipc namespace but in a mounts namespace
* which has this ipcns's mqueuefs mounted, doing some action
* with one of the mqueuefs files. That can raise the refcount.
* So dropping the refcount, and raising the refcount when
* accessing it through the VFS, are protected with mq_lock.
*
* (Clearly, a task raising the refcount on its own ipc_ns
* needn't take mq_lock since it can't race with the last task
* in the ipcns exiting).
*/
void put_ipc_ns(struct ipc_namespace *ns)
{
if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) {
mq_clear_sbinfo(ns);
spin_unlock(&mq_lock);
if (llist_add(&ns->mnt_llist, &free_ipc_list))
schedule_work(&free_ipc_work);
}
}
EXPORT_SYMBOL_GPL(put_ipc_ns);
static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns)
{
return container_of(ns, struct ipc_namespace, ns);
}
static struct ns_common *ipcns_get(struct task_struct *task)
{
struct ipc_namespace *ns = NULL;
struct nsproxy *nsproxy;
task_lock(task);
nsproxy = task->nsproxy;
if (nsproxy)
ns = get_ipc_ns(nsproxy->ipc_ns);
task_unlock(task);
return ns ? &ns->ns : NULL;
}
static void ipcns_put(struct ns_common *ns)
{
return put_ipc_ns(to_ipc_ns(ns));
}
static int ipcns_install(struct nsset *nsset, struct ns_common *new)
{
struct nsproxy *nsproxy = nsset->nsproxy;
struct ipc_namespace *ns = to_ipc_ns(new);
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
return -EPERM;
put_ipc_ns(nsproxy->ipc_ns);
nsproxy->ipc_ns = get_ipc_ns(ns);
return 0;
}
static struct user_namespace *ipcns_owner(struct ns_common *ns)
{
return to_ipc_ns(ns)->user_ns;
}
const struct proc_ns_operations ipcns_operations = {
.name = "ipc",
.type = CLONE_NEWIPC,
.get = ipcns_get,
.put = ipcns_put,
.install = ipcns_install,
.owner = ipcns_owner,
};
|